首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于非线性预测的逆传播神经网络算法优化策略研究
引用本文:丛丽晖,郑济仲,李常山.基于非线性预测的逆传播神经网络算法优化策略研究[J].沈阳航空工业学院学报,2002,19(4):32-34.
作者姓名:丛丽晖  郑济仲  李常山
作者单位:沈阳航空工业学院计算机科学与工程系,辽宁,沈阳,110034
摘    要:逆传播神经网络算法是人工神经网络用于非线性预测的主要学习算法。它具有思路清晰,结构严谨,操作性强等特点,但同时也存在预测精度低,收敛速度慢等问题,本文从神经网络模型的结构出发,对学习算法提出了一系列改进和优化措施,以加快网络的学习速度,并增加模型的稳定性。

关 键 词:非线性预测  优化  人工神经网络  逆传播学习算法
文章编号:1007-1385(2002)04-0032-03
修稿时间:2002年1月20日

Study of optimization strategy for back propagation learning algorithm based on non- linear prediction method
CONG Lihui,ZHENG Jizhong,LI Changshan.Study of optimization strategy for back propagation learning algorithm based on non- linear prediction method[J].Journal of Shenyang Institute of Aeronautical Engineering,2002,19(4):32-34.
Authors:CONG Lihui  ZHENG Jizhong  LI Changshan
Abstract:The Back Propagation Learning Algorithm is the main learning algorithm applied artificial neural network to non-linear prediction, and has the characteristics of clear thinking, precise structure and strong maneuverability. But it also has some problems such as low prediction precision, slow convergence speed and so on. With the study of neural network model, this paper advances some of improvement and optimization techniques that can accelerate the learning speed of network and increase the stability of model.
Keywords:artificial neural network  non-linear prediction  back propagation learning algorithm  optimization
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号